Exp1: PPI Network analysis
2025-11-24
1. extract PPI data
library(clusterProfiler)## ## clusterProfiler v4.16.0 Learn more at https://yulab-smu.top/contribution-knowledge-mining/
##
## Please cite:
##
## G Yu. Thirteen years of clusterProfiler. The Innovation. 2024,
## 5(6):100722##
## Attaching package: 'clusterProfiler'## The following object is masked from 'package:stats':
##
## filterlibrary(igraph)##
## Attaching package: 'igraph'## The following object is masked from 'package:clusterProfiler':
##
## simplify## The following objects are masked from 'package:stats':
##
## decompose, spectrum## The following object is masked from 'package:base':
##
## unionseed.protein <- c("APP", "PSEN1", "PSEN2", "APOE", "TREM2", "CR1")
protein.info <- read.table("./9606.protein.info.v12.0.txt", sep='\t', header=T, check.names=F, comment.char="", quote="")
head(protein.info[,seq(2)])## #string_protein_id preferred_name
## 1 9606.ENSP00000000233 ARF5
## 2 9606.ENSP00000000412 M6PR
## 3 9606.ENSP00000001008 FKBP4
## 4 9606.ENSP00000001146 CYP26B1
## 5 9606.ENSP00000002125 NDUFAF7
## 6 9606.ENSP00000002165 FUCA2ppi <- read.table("./9606.protein.links.v12.0.txt", header = T, check.names = F, comment.char = "", quote = "")
seed.protein2 <- protein.info[protein.info$preferred_name %in% seed.protein, 1]
target.ppi <- ppi |> dplyr::filter(protein1 %in% seed.protein2 | protein2 %in% seed.protein2) |>
dplyr::filter(combined_score>600)
target.ppi$protein1 <- protein.info[match(target.ppi$protein1, protein.info$`#string_protein_id`), 2]
target.ppi$protein2 <- protein.info[match(target.ppi$protein2, protein.info$`#string_protein_id`), 2]
target.ppi |> write.table("./target_ppi.tsv", sep="\t", row.names=F, col.names=T, quote=F)2. build igraph object
## load ppi network
target_ppi_g <- graph_from_data_frame(target.ppi, directed=FALSE)
target_ppi_g |> V() |> length()## [1] 571target_ppi_g |> E() |> length()## [1] 1674## simplify network
g_ppi <- simplify(target_ppi_g, remove.multiple = FALSE, remove.loops = TRUE)
g_ppi <- simplify(g_ppi, remove.multiple = TRUE, remove.loops = FALSE,
edge.attr.comb = "max")3. Network topological analysis
## load TCMDATA locally
# remotes::install_github("Hinna0818/TCMDATA)
# library(TCMDATA)
devtools::load_all("/Users/hinna/TCMDATA")## ℹ Loading TCMDATA## compute node info
g_ppi <- compute_nodeinfo(g_ppi)## Calculating degree / strength ...
## Calculating betweenness (unweighted) ...
## Calculating closeness (unweighted) ...
## Calculating eigenvector centrality ...
## Calculating PageRank ...
## Calculating coreness (k-core) ...
## Calculating local clustering coefficient ...
## Calculating eccentricity ...
## Detecting articulation points ...
## Calculating MCC ...
## Calculating MNC ...
## Calculating DMNC ...
## Calculating BottleNeck (BN) ...
## Calculating radiality ...
## Calculating Stress ...
## Calculating EPC ...## | | | 0% | | | 1% | |= | 1% | |= | 2% | |== | 2% | |== | 3% | |== | 4% | |=== | 4% | |=== | 5% | |==== | 5% | |==== | 6% | |===== | 6% | |===== | 7% | |===== | 8% | |====== | 8% | |====== | 9% | |======= | 9% | |======= | 10% | |======= | 11% | |======== | 11% | |======== | 12% | |========= | 12% | |========= | 13% | |========= | 14% | |========== | 14% | |========== | 15% | |=========== | 15% | |=========== | 16% | |============ | 16% | |============ | 17% | |============ | 18% | |============= | 18% | |============= | 19% | |============== | 19% | |============== | 20% | |============== | 21% | |=============== | 21% | |=============== | 22% | |================ | 22% | |================ | 23% | |================ | 24% | |================= | 24% | |================= | 25% | |================== | 25% | |================== | 26% | |=================== | 26% | |=================== | 27% | |=================== | 28% | |==================== | 28% | |==================== | 29% | |===================== | 29% | |===================== | 30% | |===================== | 31% | |====================== | 31% | |====================== | 32% | |======================= | 32% | |======================= | 33% | |======================= | 34% | |======================== | 34% | |======================== | 35% | |========================= | 35% | |========================= | 36% | |========================== | 36% | |========================== | 37% | |========================== | 38% | |=========================== | 38% | |=========================== | 39% | |============================ | 39% | |============================ | 40% | |============================ | 41% | |============================= | 41% | |============================= | 42% | |============================== | 42% | |============================== | 43% | |============================== | 44% | |=============================== | 44% | |=============================== | 45% | |================================ | 45% | |================================ | 46% | |================================= | 46% | |================================= | 47% | |================================= | 48% | |================================== | 48% | |================================== | 49% | |=================================== | 49% | |=================================== | 50% | |=================================== | 51% | |==================================== | 51% | |==================================== | 52% | |===================================== | 52% | |===================================== | 53% | |===================================== | 54% | |====================================== | 54% | |====================================== | 55% | |======================================= | 55% | |======================================= | 56% | |======================================== | 56% | |======================================== | 57% | |======================================== | 58% | |========================================= | 58% | |========================================= | 59% | |========================================== | 59% | |========================================== | 60% | |========================================== | 61% | |=========================================== | 61% | |=========================================== | 62% | |============================================ | 62% | |============================================ | 63% | |============================================ | 64% | |============================================= | 64% | |============================================= | 65% | |============================================== | 65% | |============================================== | 66% | |=============================================== | 66% | |=============================================== | 67% | |=============================================== | 68% | |================================================ | 68% | |================================================ | 69% | |================================================= | 69% | |================================================= | 70% | |================================================= | 71% | |================================================== | 71% | |================================================== | 72% | |=================================================== | 72% | |=================================================== | 73% | |=================================================== | 74% | |==================================================== | 74% | |==================================================== | 75% | |===================================================== | 75% | |===================================================== | 76% | |====================================================== | 76% | |====================================================== | 77% | |====================================================== | 78% | |======================================================= | 78% | |======================================================= | 79% | |======================================================== | 79% | |======================================================== | 80% | |======================================================== | 81% | |========================================================= | 81% | |========================================================= | 82% | |========================================================== | 82% | |========================================================== | 83% | |========================================================== | 84% | |=========================================================== | 84% | |=========================================================== | 85% | |============================================================ | 85% | |============================================================ | 86% | |============================================================= | 86% | |============================================================= | 87% | |============================================================= | 88% | |============================================================== | 88% | |============================================================== | 89% | |=============================================================== | 89% | |=============================================================== | 90% | |=============================================================== | 91% | |================================================================ | 91% | |================================================================ | 92% | |================================================================= | 92% | |================================================================= | 93% | |================================================================= | 94% | |================================================================== | 94% | |================================================================== | 95% | |=================================================================== | 95% | |=================================================================== | 96% | |==================================================================== | 96% | |==================================================================== | 97% | |==================================================================== | 98% | |===================================================================== | 98% | |===================================================================== | 99% | |======================================================================| 99% | |======================================================================| 100%## show basic metrics
V(g_ppi)$degree |> table()##
## 1 2 3 4 5 45 54 74 100 244 330
## 374 145 27 13 6 1 1 1 1 1 1## show the relationship between cci and degree and betweenness
library(tidygraph)##
## Attaching package: 'tidygraph'
##
## The following object is masked from 'package:igraph':
##
## groups
##
## The following object is masked from 'package:stats':
##
## filterlibrary(tibble)##
## Attaching package: 'tibble'
##
## The following object is masked from 'package:igraph':
##
## as_data_framelibrary(ggfun)## ggfun v0.2.0 Learn more at https://yulab-smu.top/library(ggplot2)## Warning: package 'ggplot2' was built under R version 4.5.2library(ggrepel)
library(ggiraph)
g_ppi |> as_tbl_graph() |>
activate('nodes') |>
tibble::as_tibble() |>
ggplot(aes(x = degree, y = clustering_coef, size = betweenness)) +
geom_point() +
geom_text_repel(data = td_filter(degree > 80), mapping = aes(label = name)) ## It is a zero-scale network
show the PPI network
library(ggtangle)## ggtangle v0.0.7 Learn more at https://yulab-smu.top/library(ggiraph)
library(ggraph)
p1 <- ggtangle::ggplot(g_ppi, layout = "kk") +
geom_edge(alpha = 0.4) +
geom_text_repel(data = td_filter(degree > 60), aes(label = name), size = 3, segment.color = NA, colour = "red2", fontface = "bold") +
geom_point(aes(color = degree, size = betweenness)) +
scale_color_viridis_c()
p1
p11 <- ggraph(g_ppi, layout = 'kk') +
geom_edge_link() +
geom_point_interactive(
mapping = aes(
x = x, y = y,
color = betweenness,
tooltip = name,
data_id = name
)
) +
geom_text_repel(data = td_filter(degree > 60),
mapping = aes(x = x, y = y, label = name), bg.color ='white'
) +
scale_color_viridis_c() +
theme_graph()
girafe(ggobj = p11)4. Network community analysis
## louvain clustering
set.seed(42)
g_ppi <- run_louvain(g_ppi)## No weights found. Running unweighted clustering.## Running Louvain (Resolution: 1.0)...## Done! Identified 5 modules (Modularity: 0.472).p2 <- ggtangle::ggplot(g_ppi, layout = "kk") +
geom_edge(alpha = 0.4) +
geom_point(aes(color = as.factor(louvain_cluster), size = betweenness)) +
geom_text_repel(data = td_filter(degree > 60), aes(label = name), size = 3, segment.color = NA, colour = "red2", fontface = "bold") +
scale_color_viridis_d() +
labs(color = "Cluster")
p2
Feature selection
topnodes_info <- rank_ppi_nodes(g = g_ppi)## Available metrics in graph: name, degree, strength, betweenness, betweenness_w, closeness, closeness_w, eigen_centrality, pagerank, coreness, clustering_coef, eccentricity, is_articulation, MCC, MNC, DMNC, BN, radiality, Stress, EPC, louvain_cluster## Using the following metrics for ranking: degree, betweenness_w, closeness_w, eccentricity, radiality, Stress, MCC, MNC, DMNC, BN, EPCg_ppi <- topnodes_info[["graph"]]
topnodes <- topnodes_info[["table"]]
## radar plot
node_profile <- get_node_profile(topnodes, node_name = "APOE",
metrics = c("degree",
"betweenness",
"closeness",
"MCC",
"MNC",
"pagerank",
"coreness",
"EPC"))
p_radar <- radar_plot(node_profile, title = "Centrality score of APOE")
p_radar
5. Network functional modules analysis
library(enrichplot)## Warning: package 'enrichplot' was built under R version 4.5.1## enrichplot v1.28.4 Learn more at https://yulab-smu.top/contribution-knowledge-mining/
##
## Please cite:
##
## Guangchuang Yu, Li-Gen Wang, Guang-Rong Yan, Qing-Yu He. DOSE: an
## R/Bioconductor package for Disease Ontology Semantic and Enrichment
## analysis. Bioinformatics. 2015, 31(4):608-609##
## Attaching package: 'enrichplot'## The following object is masked from 'package:ggfun':
##
## volplotlibrary(org.Hs.eg.db)## Loading required package: AnnotationDbi## Loading required package: stats4## Loading required package: BiocGenerics## Loading required package: generics##
## Attaching package: 'generics'## The following object is masked from 'package:TCMDATA':
##
## components## The following objects are masked from 'package:igraph':
##
## components, union## The following objects are masked from 'package:base':
##
## as.difftime, as.factor, as.ordered, intersect, is.element, setdiff,
## setequal, union##
## Attaching package: 'BiocGenerics'## The following objects are masked from 'package:igraph':
##
## normalize, path## The following objects are masked from 'package:stats':
##
## IQR, mad, sd, var, xtabs## The following objects are masked from 'package:base':
##
## anyDuplicated, aperm, append, as.data.frame, basename, cbind,
## colnames, dirname, do.call, duplicated, eval, evalq, Filter, Find,
## get, grep, grepl, is.unsorted, lapply, Map, mapply, match, mget,
## order, paste, pmax, pmax.int, pmin, pmin.int, Position, rank,
## rbind, Reduce, rownames, sapply, saveRDS, table, tapply, unique,
## unsplit, which.max, which.min## Loading required package: Biobase## Welcome to Bioconductor
##
## Vignettes contain introductory material; view with
## 'browseVignettes()'. To cite Bioconductor, see
## 'citation("Biobase")', and for packages 'citation("pkgname")'.##
## Attaching package: 'Biobase'## The following object is masked from 'package:TCMDATA':
##
## content## Loading required package: IRanges## Loading required package: S4Vectors##
## Attaching package: 'S4Vectors'## The following objects are masked from 'package:tidygraph':
##
## active, rename## The following object is masked from 'package:clusterProfiler':
##
## rename## The following object is masked from 'package:utils':
##
## findMatches## The following objects are masked from 'package:base':
##
## expand.grid, I, unname##
## Attaching package: 'IRanges'## The following object is masked from 'package:tidygraph':
##
## slice## The following objects are masked from 'package:TCMDATA':
##
## desc, slice## The following object is masked from 'package:clusterProfiler':
##
## slice##
## Attaching package: 'AnnotationDbi'## The following object is masked from 'package:tidygraph':
##
## select## The following object is masked from 'package:TCMDATA':
##
## select## The following object is masked from 'package:clusterProfiler':
##
## select## module.genes <- g_ppi |> as_tbl_graph() |> activate('nodes') |>tibble::as_tibble()
module.ora.res <- compareCluster(name ~ louvain_cluster, data = module.genes, fun = enrichGO, keyType = "SYMBOL", OrgDb=org.Hs.eg.db, ont = "BP")
dotplot(module.ora.res, label_format = 70)## Warning: `aes_string()` was deprecated in ggplot2 3.0.0.
## ℹ Please use tidy evaluation idioms with `aes()`.
## ℹ See also `vignette("ggplot2-in-packages")` for more information.
## ℹ The deprecated feature was likely used in the enrichplot package.
## Please report the issue at
## <https://github.com/GuangchuangYu/enrichplot/issues>.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
choose cluster 1 for further functional enrichment analysis
# select cluster 1 nodes
c1_nodes <- V(g_ppi)$name[V(g_ppi)$louvain_cluster == "1"]
subg_cluster1 <- induced_subgraph(g_ppi, vids = c1_nodes)
# cluster 1 enrichment analysis
c1 <- enrichGO(c1_nodes, OrgDb='org.Hs.eg.db', keyType="SYMBOL", ont = "all")
c1go <- gglollipop(c1, line.col = "orange", split = "ONTOLOGY",
line.type = "dashed", palette = "PiYG", top_n = 5, show_count = F) +
facet_grid(ONTOLOGY ~ ., scales = "free_y") +
theme(strip.text.y = element_text(angle = 0))
c1go